Revert "Simplify handling of builtin with inline redefinition"

This reverts commit 3d6f49a569.

Broke bot: https://lab.llvm.org/buildbot/#/builders/5/builds/12360

clang/lib/CodeGen/CodeGenFunction.cpp

@@ -1294,11 +1294,6 @@ void CodeGenFunction::GenerateCode(GlobalDecl GD, llvm::Function *Fn,
   FunctionArgList Args;
   QualType ResTy = BuildFunctionArgList(GD, Args);
 
-  // Give a different name to inline builtin to avoid conflict with actual
-  // builtins.
-  if (FD->isInlineBuiltinDeclaration() && Fn)
-    Fn->setName(Fn->getName() + ".inline");
-
   // Check if we should generate debug info for this function.
   if (FD->hasAttr<NoDebugAttr>()) {
     // Clear non-distinct debug info that was possibly attached to the function

clang/lib/CodeGen/CodeGenModule.cpp

@@ -3169,11 +3169,6 @@ bool CodeGenModule::shouldEmitFunction(GlobalDecl GD) {
     }
   }
 
-  // Inline builtins declaration must be emitted. They often are fortified
-  // functions.
-  if (F->isInlineBuiltinDeclaration())
-    return true;
-
   // PR9614. Avoid cases where the source code is lying to us. An available
   // externally function should have an equivalent function somewhere else,
   // but a function that calls itself through asm label/`__builtin_` trickery is

clang/test/CodeGen/memcpy-inline-builtin.c

@@ -1,44 +0,0 @@
-// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
-
-// RUN: %clang_cc1 -triple x86_64 -S -emit-llvm -o - %s | FileCheck %s
-//
-// Verifies that clang detects memcpy inline version and uses it instead of the builtin.
-
-typedef unsigned long size_t;
-
-// Clang requires these attributes for a function to be redefined.
-#define AVAILABLE_EXTERNALLY extern inline __attribute__((always_inline)) __attribute__((gnu_inline))
-
-// Clang recognizes an inline builtin and renames it to prevent conflict with builtins.
-AVAILABLE_EXTERNALLY void *memcpy(void *a, const void *b, size_t c) {
-  asm("# memcpy.inline marker");
-  return __builtin_memcpy(a, b, c);
-}
-
-// CHECK-LABEL: @foo(
-// CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[A_ADDR_I:%.*]] = alloca i8*, align 8
-// CHECK-NEXT:    [[B_ADDR_I:%.*]] = alloca i8*, align 8
-// CHECK-NEXT:    [[C_ADDR_I:%.*]] = alloca i64, align 8
-// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca i8*, align 8
-// CHECK-NEXT:    [[B_ADDR:%.*]] = alloca i8*, align 8
-// CHECK-NEXT:    [[C_ADDR:%.*]] = alloca i64, align 8
-// CHECK-NEXT:    store i8* [[A:%.*]], i8** [[A_ADDR]], align 8
-// CHECK-NEXT:    store i8* [[B:%.*]], i8** [[B_ADDR]], align 8
-// CHECK-NEXT:    store i64 [[C:%.*]], i64* [[C_ADDR]], align 8
-// CHECK-NEXT:    [[TMP0:%.*]] = load i8*, i8** [[A_ADDR]], align 8
-// CHECK-NEXT:    [[TMP1:%.*]] = load i8*, i8** [[B_ADDR]], align 8
-// CHECK-NEXT:    [[TMP2:%.*]] = load i64, i64* [[C_ADDR]], align 8
-// CHECK-NEXT:    store i8* [[TMP0]], i8** [[A_ADDR_I]], align 8
-// CHECK-NEXT:    store i8* [[TMP1]], i8** [[B_ADDR_I]], align 8
-// CHECK-NEXT:    store i64 [[TMP2]], i64* [[C_ADDR_I]], align 8
-// CHECK-NEXT:    call void asm sideeffect "# memcpy.inline marker", "~{dirflag},~{fpsr},~{flags}"() #[[ATTR2:[0-9]+]], !srcloc !2
-// CHECK-NEXT:    [[TMP3:%.*]] = load i8*, i8** [[A_ADDR_I]], align 8
-// CHECK-NEXT:    [[TMP4:%.*]] = load i8*, i8** [[B_ADDR_I]], align 8
-// CHECK-NEXT:    [[TMP5:%.*]] = load i64, i64* [[C_ADDR_I]], align 8
-// CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 [[TMP3]], i8* align 1 [[TMP4]], i64 [[TMP5]], i1 false) #[[ATTR2]]
-// CHECK-NEXT:    ret void
-//
-void foo(void *a, const void *b, size_t c) {
-  memcpy(a, b, c);
-}

clang/test/CodeGen/memcpy-no-nobuiltin-if-not-emitted.c

@@ -0,0 +1,25 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
+//
+// Verifies that clang doesn't mark an inline builtin definition as `nobuiltin`
+// if the builtin isn't emittable.
+
+typedef unsigned long size_t;
+
+// always_inline is used so clang will emit this body. Otherwise, we need >=
+// -O1.
+#define AVAILABLE_EXTERNALLY extern inline __attribute__((always_inline)) \
+    __attribute__((gnu_inline))
+
+AVAILABLE_EXTERNALLY void *memcpy(void *a, const void *b, size_t c) {
+  return __builtin_memcpy(a, b, c);
+}
+
+// CHECK-LABEL: define{{.*}} void @foo
+void foo(void *a, const void *b, size_t c) {
+  // Clang will always _emit_ this as memcpy. LLVM turns it into @llvm.memcpy
+  // later on if optimizations are enabled.
+  // CHECK: call i8* @memcpy
+  memcpy(a, b, c);
+}
+
+// CHECK-NOT: nobuiltin

clang/test/CodeGen/memcpy-nobuiltin.c

@@ -4,8 +4,7 @@
 //
 // CHECK-WITH-DECL-NOT: @llvm.memcpy
 // CHECK-NO-DECL: @llvm.memcpy
-// CHECK-SELF-REF-DECL-LABEL: define dso_local i8* @memcpy.inline
-// CHECK-SELF-REF-DECL:       @memcpy(
+// CHECK-SELF-REF-DECL: @llvm.memcpy
 //
 #include <memcpy-nobuiltin.inc>
 void test(void *dest, void const *from, size_t n) {

clang/test/CodeGen/pr9614.c

@@ -32,14 +32,14 @@ void f(void) {
 
 // CHECK-LABEL: define{{.*}} void @f()
 // CHECK: call void @foo()
-// CHECK: call i32 @abs(i32 %0)
+// CHECK: call i32 @abs(i32 0)
 // CHECK: call i8* @strrchr(
 // CHECK: call void @llvm.prefetch.p0i8(
 // CHECK: call i8* @memchr(
 // CHECK: ret void
 
 // CHECK: declare void @foo()
+// CHECK: declare i32 @abs(i32
 // CHECK: declare i8* @strrchr(i8*, i32)
 // CHECK: declare i8* @memchr(
-// CHECK: declare i32 @abs(i32
 // CHECK: declare void @llvm.prefetch.p0i8(